Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to realization and understanding of truths or important concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phan
    -0.17
    ?url
    -0.14
    @brief
    -0.14
    еÑģÑĮ
    -0.14
    owers
    -0.13
    uest
    -0.13
    235
    -0.13
     ä½į
    -0.13
    سط
    -0.13
    ondon
    -0.13
    POSITIVE LOGITS
    rung
    0.16
    assi
    0.15
    ra
    0.14
    raft
    0.14
    80
    0.14
    125
    0.14
    æŀ
    0.14
    75
    0.14
    ei
    0.14
    zers
    0.14
    Act Density 0.095%

    No Known Activations